import PropertiesTable from "@site/src/components/PropertiesTable";

chatRoute()

Creates a chat route handler for streaming agent conversations using the AI SDK format. This function registers an HTTP POST endpoint that accepts messages, executes an agent, and streams the response back to the client in AI SDK-compatible format. You have to use it inside a custom API route.

Use handleChatStream() if you need a framework-agnostic handler.

chatRoute() keeps the existing AI SDK v5/default behavior. If your app is typed against AI SDK v6, pass version: 'v6'.

:::note Disconnect behavior

chatRoute() forwards the incoming request's AbortSignal to agent.stream(). If the client disconnects, Mastra aborts the in-flight generation.

If you want the server to continue generation and persist the final response after disconnect, build a custom API route around agent.stream() and call consumeStream() on the returned MastraModelOutput.

:::

Usage example

This example shows how to set up a chat route at the /chat endpoint that uses an agent with the ID weatherAgent.

import { Mastra } from '@mastra/core'
import { chatRoute } from '@mastra/ai-sdk'

export const mastra = new Mastra({
  server: {
    apiRoutes: [
      chatRoute({
        path: '/chat',
        agent: 'weatherAgent',
      }),
    ],
  },
})

You can also use dynamic agent routing based on an agentId. The URL /chat/weatherAgent will resolve to the agent with the ID weatherAgent.

import { Mastra } from '@mastra/core'
import { chatRoute } from '@mastra/ai-sdk'

export const mastra = new Mastra({
  server: {
    apiRoutes: [
      chatRoute({
        path: '/chat/:agentId',
      }),
    ],
  },
})

Parameters

<PropertiesTable content={[ { name: 'version', type: "'v5' | 'v6'", description: "Selects the AI SDK stream contract to emit. Omit it or pass 'v5' for the existing default behavior. Pass 'v6' when your app is typed against AI SDK v6 response helpers.", isOptional: true, defaultValue: "'v5'", }, { name: 'path', type: 'string', description: 'The route path (e.g., /chat or /chat/:agentId). Include :agentId for dynamic agent routing.', isOptional: false, defaultValue: "'/chat/:agentId'", }, { name: 'agent', type: 'string', description: "The ID of the agent to use for this chat route. Required if the path doesn't include :agentId.", isOptional: true, }, { name: 'defaultOptions', type: 'AgentExecutionOptions', description: 'Default options passed to agent execution. These can include instructions, memory configuration, maxSteps, and other execution settings.', isOptional: true, }, { name: 'sendStart', type: 'boolean', description: 'Whether to send start events in the stream.', isOptional: true, defaultValue: 'true', }, { name: 'sendFinish', type: 'boolean', description: 'Whether to send finish events in the stream.', isOptional: true, defaultValue: 'true', }, { name: 'sendReasoning', type: 'boolean', description: 'Whether to include reasoning steps in the stream.', isOptional: true, defaultValue: 'false', }, { name: 'sendSources', type: 'boolean', description: 'Whether to include source citations in the stream.', isOptional: true, defaultValue: 'false', }, ]} />

Additional configuration

You can use prepareSendMessagesRequest to customize the request sent to the chat route, for example to pass additional configuration to the agent:

const { error, status, sendMessage, messages, regenerate, stop } = useChat({
  transport: new DefaultChatTransport({
    api: 'http://localhost:4111/chat',
    prepareSendMessagesRequest({ messages }) {
      return {
        body: {
          messages,
          // Pass memory config
          memory: {
            thread: 'user-1',
            resource: 'user-1',
          },
        },
      }
    },
  }),
})